ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models
Contextual entrainment is the tendency of a model to let auxiliary context in its input pull its output, independently of whether that context is relevant, true, or even meaningful. Recently, it has been identified and given a mechanistic account in unimodal language models. Whether and how it manifests in vision-language models (VLMs) is, by contrast, largely unexamined, and the field lacks a purpose-built instrument with which to investigate it. We take the position that studying contextual entrainment in VLMs requires more than porting an existing text-only benchmark to the multimodal setti
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%VioletVision-3B →
“Fuzzy title match (0.73): “ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment” ≈ “VioletVision-3B””
- FuzzySimilar title/name (fuzzy) · 84%pytorch/vision →
“Fuzzy title match (0.92): “ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment” ≈ “pytorch/vision””
- LinkedLinked via arxiv author · 85%Karan Goyal →
“ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models”
- LinkedLinked via arxiv author · 85%Afreen Hossain →
“ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models”
- LinkedLinked via arxiv author · 85%Debojyoti Das →
“ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models”
- LinkedLinked via arxiv author · 85%Vishal Bhutani →
“ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models”